Workflow
The following is a typical workflow for using H2O Eval Studio.
Add a model to the host of the LLM models you want to evaluate. For more information, see Add a model host.
Create or import a test suite with prompts, expected answers, and (for RAG evaluation) a corpus of documents. For more information, see Tests.
Create a dashboard or leaderboard by running an evaluation.
View a visualization of the dashboard or leaderboard, obtain an HTML report, and download a zip archive with the evaluation results.
Feedback
- Submit and view feedback for this page
- Send feedback about H2O Eval Studio to cloud-feedback@h2o.ai